Issues in XAI #5: “Understanding Black Boxes: Interdisciplinary Perspectives”

Ort: Dortmund
Beginn: 05.09.2022 11:00
Ende: 07.09.2022 14:00

Artificial intelligent (AI) systems are used in many (high-stakes) contexts. However, it is difficult to evaluate their fairness or trustworthiness since they often depend on complex algorithms. The field of explainable artificial intelligence (XAI) develops methods to make such systems understandable by means of explanations.

But what does it mean to understand an (opaque) system or its outputs? What is the link between explanations and understanding? How do different contexts (e.g. legal vs. medical) affect explainability and understandability? What can theories of understanding and explanation from psychology and philosophy contribute to XAI? How do these insights mesh with explainability approaches from computer science?

Our workshop aims to shed light on these and related questions and will bring together researchers from philosophy, psychology, computer science, and law to push forward research on understanding and XAI.

The workshop is organized within the research project “Explainable Intelligent Systems”. It is the 5th installment of the workshop series “Issues in XAI”, which is co-organized by EIS and its partners, the Leverhulme Centre for the Future of Intelligence (Cambridge), TU Delft, and the project BIAS (Leibniz University Hannover). Both the EIS project and the workshop are funded by the Volkswagen Foundation.

Organizers: Eva Schmidt, Sara Mann

Please register via e-mail with subject header “Registration” to sara.mann@tu-dortmund.de by August 22, 2022.

Veranstaltung melden
Stellenausschreibung melden